Closes #956

bigbio/hub/hub_repos/studytypeteller/README.md

@@ -0,0 +1,66 @@
+---
+language:
+  - en [This needs to be a supported huggingface language code]
+bigbio_language:
+  - English
+license: apache-2.0 [this shoudl be a supported huggingface license]
+bigbio_license_shortname: APACHE_2p0
+multilinguality: monolingual
+pretty_name: StudyTypeTeller
+homepage: https://github.com/Ineichen-Group/StudyTypeTeller/tree/main
+bigbio_pubmed: true
+bigbio_public: true
+bigbio_tasks:
+  - TEXT_CLASSIFICATION
+---
+
+
+# Dataset Card for StudyTypeTeller
+
+## Dataset Description
+
+- **Homepage:** https://github.com/Ineichen-Group/StudyTypeTeller/tree/main
+- **Pubmed:** True
+- **Public:** True
+- **Tasks:** TXTCLASS
+
+
+The dataset consists of 2,645 PubMed titles and abstracts, manually annotated for study type classification in the biomedical domain. 
+This corpus is designed to support automated classification of study types and to facilitate research on reducing the workload associated with abstract screening in systematic reviews.
+
+Each record is labeled according to one of 14 predefined study types.
+The annotations were created by human experts, and include the following categories:
+
+| Category                                      | Train | Validation | Test | Total |
+|----------------------------------------------|------:|-----------:|-----:|------:|
+| **Corpus size**                              | 1,581 |        530 |  534 | 2,645 |
+| **Multiclass labels**                        |       |            |      |       |
+| Remaining                                    |   514 |        172 |  172 |   858 |
+| Non-systematic-review                        |   222 |         74 |   75 |   371 |
+| Human-non-RCT-non-drug-intervention          |   123 |         41 |   42 |   206 |
+| Human-non-RCT-drug-intervention              |   107 |         36 |   36 |   179 |
+| Human-case-report                            |    99 |         33 |   33 |   165 |
+| Animal-other                                 |    93 |         31 |   31 |   155 |
+| Animal-drug-intervention                     |    88 |         29 |   30 |   147 |
+| Human-systematic-review                      |    66 |         22 |   22 |   110 |
+| In-vitro-study                               |    62 |         21 |   21 |   104 |
+| Human-RCT-non-drug-intervention              |    52 |         18 |   18 |    88 |
+| Animal-non-drug-intervention                 |    46 |         15 |   16 |    77 |
+| Human-RCT-drug-intervention                  |    43 |         15 |   15 |    73 |
+| Clinical-study-protocol                      |    34 |         12 |   12 |    58 |
+| Human-RCT-non-intervention                   |    32 |         11 |   11 |    54 |
+
+## Citation Information
+
+```
+@article{doneva2025studytypeteller,
+  author    = {Doneva, Emilova S and de Viragh, S and Hubarava, H and Schandelmaier, S and Briel, M and Ineichen, BV},
+  title     = {StudyTypeTeller—Large language models to automatically classify research study types for systematic reviews},
+  journal   = {Research Synthesis Methods},
+  volume    = {16},
+  number    = {6},
+  pages     = {1005--1024},
+  year      = {2025},
+  doi       = {10.1017/rsm.2025.10031}
+}
+```